(219 days)
L Vivo platform is intended for non-invasive processing of ultrasound images to detect, measure, and calculate relevant medical parameters of structures and function of patients with suspected disease. In addition, it has the ability to provide Quality Score feedback.
The LVivo platform is a software system for automated analysis of ultrasound examinations. Automated analysis of echocardiographic examinations is done using DICOM movies. The LVivo platform supports global and segmental evaluation of the left ventricle (LV) of the heart. The global LV function is evaluated from two of the apical views: four-chamber (4CH) and two-chamber (2CH) by ejection fraction (EF). The segmental LV function is done from three apical views 4CH, 2CH and three chamber (3CH) and supports wall motion evaluation and strain. The LVivo platform supports also global and segmental evaluation of the LV from the parasternal Short Axis (SAX) view and the Parasternal Long Axis view (PLAX).
LVivo PLAX extends the current toolbox of the LVivo platform, providing automated calculation of LV size and function parameters from the PLAX view, for cardiac function evaluation as part of the standard echocardiographic assessment in Echo environment and point-of-care. The measurements from the PLAX view add information about the contraction of the LV, its size and wall thickness and can be used for rapid evaluation of the patient's condition in the point-of-care.
In addition to the LV analysis, the cardiology toolbox includes a module for automated evaluation of the Right Ventricular function and the LVivo Seamless. The LVivo platform includes one additional non-cardiac module for the measurement of the bladder volume.
Here's an analysis of the acceptance criteria and study as requested, based on the provided text:
1. Table of Acceptance Criteria and Reported Device Performance
| Parameter | Acceptance Criteria | Reported Device Performance (Primary Study) | Reported Device Performance (Additional Dataset - LVivo PLAX) |
|---|---|---|---|
| FS | correlation >=75% vs manual measurements | r=0.79 | Corr: 0.74* |
| LVIDd | (Not explicitly stated, but implied by 'Results acceptance considered bias and LOA as well as correlation for the calculated parameters') | N/A | Corr: 0.9, Bias: 0.3cm, LOA: -0.2, 0.9 |
| LVIDs | (Not explicitly stated) | N/A | Corr: 0.95, Bias: 0.42cm, LOA: -0.25, 1.1 |
| IVSD | (Not explicitly stated) | N/A | Corr: 0.72, Bias: -0.16cm, LOA: -0.47, 0.13 |
| PWD | (Not explicitly stated) | N/A | Corr: 0.68, Bias: -0.095cm, LOA: -0.21, 0.4 |
| LV Mass | (Not explicitly stated) | N/A | Corr: 0.94, Bias: 9.14gr, LOA: -41.6, 59.88 |
| Automatic Analysis Rate | Not explicitly stated as acceptance criteria, but reported | 82% | 90% |
Note: The acceptance criteria for parameters other than FS are not explicitly stated in the provided text, but the results for correlation, bias, and LOA are reported, implying these were considered for acceptance. The FS correlation of 0.74 for the additional dataset is slightly below the 0.75 acceptance criteria, but the text states "The primary end point was met" and makes an overall conclusion of substantial equivalence, implying this difference was deemed acceptable in context.
2. Sample Size Used for the Test Set and Data Provenance
- Primary Clinical Validation:
- Sample Size: 121 patients
- Data Provenance: Not explicitly stated, but mentioned to be "according to GCP standards."
- Retrospective or Prospective: Not explicitly stated.
- Additional Dataset (for LVivo PLAX validation):
- Sample Size: 40 patients
- Data Provenance: USA-based medical center
- Retrospective or Prospective: Not explicitly stated.
3. Number of Experts Used to Establish the Ground Truth for the Test Set and Their Qualifications
- Number of Experts: Two sonographers.
- Qualifications: Not explicitly stated beyond "sonographers."
4. Adjudication Method for the Test Set
- The text states "The correlation vs average manual measurements of two sonographers." This suggests a method of averaging measurements from two experts to establish the ground truth. It is not a 2+1 or 3+1 adjudication method where a third expert breaks ties, but rather a consensus via averaging.
5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study
- There is no mention of an MRMC comparative effectiveness study done to compare human readers with and without AI assistance. The study focuses on the standalone performance of the AI against human measurements.
6. Standalone Performance Study
- Yes, a standalone performance study was done. The study compares the LVivo Software Application's automated analysis results against manual measurements performed by sonographers. For the primary study, 82% of exams were automatically analyzed, and for the additional dataset, 90% were automatically analyzed, indicating standalone algorithm-only performance.
7. Type of Ground Truth Used
- Expert Consensus (via averaging): The ground truth was established by "average manual measurements of two sonographers."
8. Sample Size for the Training Set
- The document does not provide information regarding the sample size used for the training set. This information is typically proprietary to the manufacturer and not released in 510(k) summaries unless specifically required or relevant for substantial equivalence claims.
9. How the Ground Truth for the Training Set Was Established
- The document does not provide information on how the ground truth for the training set was established. This is also typically proprietary and not typically included in these types of summary documents.
§ 892.2050 Medical image management and processing system.
(a)
Identification. A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).